linkpix-vidu-q2-clone

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to ask the user for an API key and then use it directly in a command-line argument (qhkit config set --token <密钥>), which passes the credential through the LLM context and output, creating a secret exposure risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow ingests text via video-inspire from video sharing links (e.g., Douyin) which can contain outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs the agent to install Node.js via curl from nodejs.org during runtime environment setup, which fits the criteria for remote code execution via installation scripts.